Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Surgery Surgery

Development and Validation of Image-Based Deep Learning Models to Predict Surgical Complexity and Complications in Abdominal Wall Reconstruction.

In JAMA surgery ; h5-index 69.0

Importance : Image-based deep learning models (DLMs) have been used in other disciplines, but this method has yet to be used to predict surgical outcomes.

Objective : To apply image-based deep learning to predict complexity, defined as need for component separation, and pulmonary and wound complications after abdominal wall reconstruction (AWR).

Design, Setting, and Participants : This quality improvement study was performed at an 874-bed hospital and tertiary hernia referral center from September 2019 to January 2020. A prospective database was queried for patients with ventral hernias who underwent open AWR by experienced surgeons and had preoperative computed tomography images containing the entire hernia defect. An 8-layer convolutional neural network was generated to analyze image characteristics. Images were batched into training (approximately 80%) or test sets (approximately 20%) to analyze model output. Test sets were blinded from the convolutional neural network until training was completed. For the surgical complexity model, a separate validation set of computed tomography images was evaluated by a blinded panel of 6 expert AWR surgeons and the surgical complexity DLM. Analysis started February 2020.

Exposures : Image-based DLM.

Main Outcomes and Measures : The primary outcome was model performance as measured by area under the curve in the receiver operating curve (ROC) calculated for each model; accuracy with accompanying sensitivity and specificity were also calculated. Measures were DLM prediction of surgical complexity using need for component separation techniques as a surrogate and prediction of postoperative surgical site infection and pulmonary failure. The DLM for predicting surgical complexity was compared against the prediction of 6 expert AWR surgeons.

Results : A total of 369 patients and 9303 computed tomography images were used. The mean (SD) age of patients was 57.9 (12.6) years, 232 (62.9%) were female, and 323 (87.5%) were White. The surgical complexity DLM performed well (ROC = 0.744; P < .001) and, when compared with surgeon prediction on the validation set, performed better with an accuracy of 81.3% compared with 65.0% (P < .001). Surgical site infection was predicted successfully with an ROC of 0.898 (P < .001). However, the DLM for predicting pulmonary failure was less effective with an ROC of 0.545 (P = .03).

Conclusions and Relevance : Image-based DLM using routine, preoperative computed tomography images was successful in predicting surgical complexity and more accurate than expert surgeon judgment. An additional DLM accurately predicted the development of surgical site infection.

Elhage Sharbel Adib, Deerenberg Eva Barbara, Ayuso Sullivan Armando, Murphy Keith Joseph, Shao Jenny Meng, Kercher Kent Williams, Smart Neil James, Fischer John Patrick, Augenstein Vedra Abdomerovic, Colavita Paul Dominick, Heniford B Todd


oncology Oncology

Knowledge-based radiation treatment planning: A data-driven method survey.

In Journal of applied clinical medical physics ; h5-index 28.0

This paper surveys the data-driven dose prediction methods investigated for knowledge-based planning (KBP) in the last decade. These methods were classified into two major categories-traditional KBP methods and deep-learning (DL) methods-according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best-matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data-driven KBP methods to dose prediction.

Momin Shadab, Fu Yabo, Lei Yang, Roper Justin, Bradley Jeffrey D, Curran Walter J, Liu Tian, Yang Xiaofeng


data-driven methods, deep learning, knowledge-based planning, machine learning, radiation dose prediction methods, radiotherapy treatment planning

oncology Oncology

A sensitivity analysis of probability maps in deep-learning-based anatomical segmentation.

In Journal of applied clinical medical physics ; h5-index 28.0

PURPOSE : Deep-learning-based segmentation models implicitly learn to predict the presence of a structure based on its overall prominence in the training dataset. This phenomenon is observed and accounted for in deep-learning applications such as natural language processing but is often neglected in segmentation literature. The purpose of this work is to demonstrate the significance of class imbalance in deep-learning-based segmentation and recommend tuning of the neural network optimization objective.

METHODS : An architecture and training procedure were chosen to represent common models in anatomical segmentation. A family of 5-block 2D U-Nets were independently trained to segment 10 structures from the Cancer Imaging Archive's Head-Neck-Radiomics-HN1 dataset. We identify the optimal threshold for our models according to their Dice score on the validation datasets and consider perturbations about the optimum. A measure of structure prominence in segmentation datasets is defined, and its impact on the optimal threshold is analyzed. Finally, we consider the use of a 2D Dice objective in addition to binary cross entropy.

RESULTS : We observe significant decreases in perceived model performance with conventional 0.5-thresholding. Perturbations of as little as ±0.05 about the optimum threshold induce a median reduction in Dice score of 11.8% for our models. There is statistical evidence to suggest a weak correlation between training dataset prominence and optimal threshold (Pearson r = 0.92 and p 10 - 4 ). We find that network optimization with respect to the 2D Dice score itself significantly reduces variability due to thresholding but does not unequivocally create the best segmentation models when assessed with distance-based segmentation metrics.

CONCLUSION : Our results suggest that those practicing deep-learning-based contouring should consider their postprocessing procedures as a potential avenue for improved performance. For intensity-based postprocessing, we recommend a mixed objective function consisting of the traditional binary cross entropy along with the 2D Dice score.

Bice Noah, Kirby Neil, Li Ruiqi, Nguyen Dan, Bahr Tyler, Kabat Christopher, Myers Pamela, Papanikolaou Niko, Fakhreddine Mohamad


deep learning, machine learning, segmentation

General General

Systemic retinal biomarkers.

In Current opinion in ophthalmology

PURPOSE OF REVIEW : Systemic retinal biomarkers are biomarkers identified in the retina and related to evaluation and management of systemic disease. This review summarizes the background, categories and key findings from this body of research as well as potential applications to clinical care.

RECENT FINDINGS : Potential systemic retinal biomarkers for cardiovascular disease, kidney disease and neurodegenerative disease were identified using regression analysis as well as more sophisticated image processing techniques. Deep learning techniques were used in a number of studies predicting diseases including anaemia and chronic kidney disease. A virtual coronary artery calcium score performed well against other competing traditional models of event prediction.

SUMMARY : Systemic retinal biomarker research has progressed rapidly using regression studies with clearly identified biomarkers such as retinal microvascular patterns, as well as using deep learning models. Future systemic retinal biomarker research may be able to boost performance using larger data sets, the addition of meta-data and higher resolution image inputs.

Ranchod Tushar M


Ophthalmology Ophthalmology

Gaps in standards for integrating artificial intelligence technologies into ophthalmic practice.

In Current opinion in ophthalmology

PURPOSE OF REVIEW : The purpose of this review is to provide an overview of healthcare standards and their relevance to multiple ophthalmic workflows, with a specific emphasis on describing gaps in standards development needed for improved integration of artificial intelligence technologies into ophthalmic practice.

RECENT FINDINGS : Healthcare standards are an essential component of data exchange and critical for clinical practice, research, and public health surveillance activities. Standards enable interoperability between clinical information systems, healthcare information exchange between institutions, and clinical decision support in a complex health information technology ecosystem. There are several gaps in standards in ophthalmology, including relatively low adoption of imaging standards, lack of use cases for integrating apps providing artificial intelligence -based decision support, lack of common data models to harmonize big data repositories, and no standards regarding interfaces and algorithmic outputs.

SUMMARY : These gaps in standards represent opportunities for future work to develop improved data flow between various elements of the digital health ecosystem. This will enable more widespread adoption and integration of artificial intelligence-based tools into clinical practice. Engagement and support from the ophthalmology community for standards development will be important for advancing this work.

Baxter Sally L, Lee Aaron Y


Ophthalmology Ophthalmology

Applications of interpretability in deep learning models for ophthalmology.

In Current opinion in ophthalmology

PURPOSE OF REVIEW : In this article, we introduce the concept of model interpretability, review its applications in deep learning models for clinical ophthalmology, and discuss its role in the integration of artificial intelligence in healthcare.

RECENT FINDINGS : The advent of deep learning in medicine has introduced models with remarkable accuracy. However, the inherent complexity of these models undermines its users' ability to understand, debug and ultimately trust them in clinical practice. Novel methods are being increasingly explored to improve models' 'interpretability' and draw clearer associations between their outputs and features in the input dataset. In the field of ophthalmology, interpretability methods have enabled users to make informed adjustments, identify clinically relevant imaging patterns, and predict outcomes in deep learning models.

SUMMARY : Interpretability methods support the transparency necessary to implement, operate and modify complex deep learning models. These benefits are becoming increasingly demonstrated in models for clinical ophthalmology. As quality standards for deep learning models used in healthcare continue to evolve, interpretability methods may prove influential in their path to regulatory approval and acceptance in clinical practice.

Hanif Adam M, Beqiri Sara, Keane Pearse A, Campbell J Peter