In Medical physics ; h5-index 59.0
BACKGROUND : von Hippel-Lindau syndrome (VHL) is an autosomal dominant hereditary syndrome with an increased predisposition of developing numerous cysts and tumors, almost exclusively clear cell renal cell carcinoma (ccRCC). Considering the lifelong surveillance in such patients to monitor the disease, patients with VHL are preferentially imaged using MRI to eliminate radiation exposure.
PURPOSE : Segmentation of kidney and tumor structures on MRI in VHL patients is useful in lesion characterization (e.g. cyst vs. tumor), volumetric lesion analysis and tumor growth prediction. However, automated tasks such as ccRCC segmentation on MRI is sparsely studied. We develop segmentation methodology for ccRCC on T1 weighted pre-contrast, corticomedullary, nephrogenic and excretory contrast phase MRI.
METHODS : We applied a new neural network approach using a novel differentiable decision forest, called hinge forest (HF), to segment kidney parenchyma, cyst and ccRCC tumors in 117 images from 115 patients. This data set represented an unprecedented 504 ccRCCs with 1171 cystic lesions obtained at 5 different MRI scanners. The hinge forest architecture was compared with U-Net on 10 randomized splits with 75% used for training and 25% used for testing. Both methods were trained with Adam using default parameters (ɑ = 0.001, β1 = 0.9, β2 = 0.999) over 1000 epochs. We further demonstrated some interpretability of our HF method by exploiting decision tree structure.
RESULTS : The HF achieved an average kidney, cyst and tumor Dice similarity coefficient (DSC) of 0.75 ± 0.03, 0.44 ± 0.05, 0.53 ± 0.04 respectively while U-Net achieved an average kidney, cyst and tumor DSC of 0.78 ± 0.02, 0.41 ± 0.04, 0.46 ± 0.05 respectively. The HF significantly outperformed U-Net on tumors while U-Net significantly outperformed HF when segmenting kidney parenchymas (ɑ < 0.01).
CONCLUSIONS : For the task of ccRCC segmentation, the HF can offer better segmentation performance compared to the traditional U-Net architecture. The leaf maps can glean hints about deep learning features that might prove to be useful in other automated tasks such as tumor characterization.
Lay Nathan, Anari Pouria Yazdian, Chaurasia Aditi, Firouzabadi Mina Dehghani, Harmon Stephanie, Turkbey Evrim, Gautam Rabindra, Samimi Safa, Merino Maria J, Ball Mark W, Linehan W Marston, Turkbey Baris, Malayeri Ashkan
2023-Mar-01
MRI, deep learning, von Hippel-Lindau
