Computational image features of immune architecture is associated with clinical benefit and survival in gynecological cancers across treatment modalities.

BACKGROUND: We present a computational approach (ArcTIL) for quantitative characterization of the architecture of tumor-infiltrating lymphocytes (TILs) and their interplay with cancer cells from digitized H&E-stained histology whole slide images and evaluate its prognostic role in three different gynecological cancer (GC) types and across three different treatment types (platinum, radiation and immunotherapy). METHODS: In this retrospective study, we included 926 patients with GC diagnosed with ovarian cancer (OC), cervical cancer, and endometrial cancer with available digitized diagnostic histology slides and survival outcome information. ArcTIL features quantifying architecture and spatial interplay between immune cells and the rest of nucleated cells (mostly comprised cancer cells) were extracted from the cell cluster graphs of nuclei within the tumor epithelial nests, surrounding stroma and invasive tumor front compartments on H&E-stained slides. A Cox proportional hazards model, incorporating ArcTIL features was fit on the OC training cohort (N=51), yielding an ArcTIL signature. A unique threshold learned from the training set stratified the patients into a low and high-risk group. RESULTS: The seven feature ArcTIL classifier was found to significantly correlate with overall survival in chemotherapy and radiotherapy-treated validation cohorts and progression-free survival in an immunotherapy-treated validation cohort. ArcTIL features relating to increased density of TILs in the epithelium and invasive tumor front were found to be associated with better survival outcomes when compared with those patients with an increased TIL density in the stroma. A statistically significant association was found between the ArcTIL signature and signaling pathways for blood vessel morphogenesis, vasculature development, regulation of cell differentiation, cell-substrate adhesion, biological adhesion, regulation of vasculature development, and angiogenesis. CONCLUSIONS: This study reveals that computationally-derived features from the spatial architecture of TILs and tumor cells are prognostic in GCs treated with chemotherapy, radiotherapy, and checkpoint blockade and are closely associated with central biological processes that impact tumor progression. These findings could aid in identifying therapy-refractory patients and further enable personalized treatment decision-making.

A Generalized Ghost Detection and Segmentation Method for Double-Joint Photographic Experts Group Compression.

BACKGROUND: The versatility of digital photographs and vast usage of image processing tools have made the image manipulation accessible and ubiquitous. Thus, there is an urgent need to develop digital image forensics tools, specifically for joint photographic experts group (JPEG) format which is the most prevailing format for storing digital photographs. Existing double JPEG methods needs improvement to reduce their sensitivity to the random grid shifts which is highly common in manipulation scenario. Also, a fully automatic pipeline, in terms of segmentation followed by the classifier is still required. METHODS: First, a low-pass filter (with some modifications) is used to distinguish between high-textured and low-textured areas. Then, using the inconsistency values between the quality-factors, a grayscale image, called the ghost image, is constituted. To automate the whole method, a novel segmentation method is also proposed, which extracts the ghost borders. In the last step of the proposed method, using Kolmogorov-Smirnov statistic, the distance between two separated areas (ghost area and the rest of the image) is calculated and compared with a predefined threshold to confirm the presence of forgery/authenticity. RESULTS: In this study, a simple yet efficient algorithm to detect double-JPEG compression is proposed. This method reveals the sub-visual differences in the quality factor in the different parts of the image. Afterward, forgery borders are extracted and are used to assess authenticity score. In our experiments, the average specificity of our segmentation method exceeds 92% and the average precision is 75%. CONCLUSION: The final binary results for classification are compared with six state-of-the-art methods. According to several performance metrics, our method outperforms the previously proposed ones.