Computer-aided diagnosis of disease primarily depends on proper Vision Based Measurement (VBM). The traditional approach followed for diagnosis of colorectal cancer includes a manual screening of colorectum via a colonoscope and resection of polyps for histopathological analysis to decide the grade of malignancy. This procedure is time-consuming, expensive, and removal of benign polyp for analysis signifies the inefficiency of the diagnosis system. These drawbacks inspired us to develop an automatic vision-based analysis method for preliminary in-vivo malignancy analysis of the polyp region. In this work, we have proposed a fusion-based polyp segmentation network, namely Polyp-Net. Recently, Convolutional neural networks (CNNs) have shown immense success in the domain of medical image analysis as it can exploit in-depth significant features with high discrimination capabilities. So motivated by these insights, we have proposed an enriched version of CNN with a nascent pooling mechanism, namely Dual-Tree Wavelet pooled CNN (DT-WpCNN). The resultant segmented mask contains some surplus high-intensity regions apart from the polyp region. These shortcomings are avoided using a new variation of the region-based level-set method, namely the Local Gradient Weighting-embedded level set method (LGWe-LSM), which shows a significant reduction of false-positive rate. The pixel-level fusion of the two enhanced methods shows more potentiality in the segmentation of the polyp regions. Our proposed network is trained on CVC-colon DB and tested on CVC-clinic DB. It achieves a Dice-score: 0.839, Volume-similarity: 0.863, Precision: 0.836, Recall: 0.811, F1-score: 0.823, F2-score: 0.815, and Hausdorff Distance: 21.796 which outperforms the existing baseline CNN’s and recent state-of-the-art methods.

COronaVIrus Disease 2019 (COVID-19) emerged as a global pandemic in the last two years. Typical abnormal findings in chest computed tomography (CT) images of COVID-19 patients are ground-glass opacities (GGOs) and consolidation, which signify the extent of damage caused to the lungs. The manual annotation of these abnormalities for severity analysis is complex, tedious, and time-consuming. This motivated us to develop a vision-based analysis framework for automated segmentation of lung abnormalities. We proposed a deep learning framework, namely LwMLA-NET “Lightweight Multi-Level Attention-based NETwork,” to segment GGO and consolidation. The LwMLA-NET is based on an encoder–decoder architecture where depth-wise separable convolutions are employed at each stage, making it a light-weighted framework that significantly reduces the computational cost. Another distinguishable module in LwMLA-NET is the multilevel attention (MLA) mechanism that focuses on dominant and relevant features and avoids propagation of insignificant features from the encoder to the decoder, thereby aiding faster optimization. Integrating the atrous spatial pyramid pooling (ASPP) module in the bottleneck helps to handle scale variations. The LwMLA-NET was evaluated on two databases—MedSeg and Radiopedia—and obtained F1-scores of 76.7% and 73.1%, respectively. The experimental evaluation justifies that LwMLA-NET outperforms other state-of-the-art deep learning frameworks like Attention U-Net, PSP-Net, Cople-Net, Inf-Net, and Mobile-Net V2 in terms of segmentation performance and has an acceptable generalization capability. Moreover, our team, “LwMLA-NET-Team-KDD-JU,” participated in Kaggle’s “COVID-19 CT Images Segmentation” open challenge. The performance was evaluated on a separate test set, and we obtained fourth rank on the leaderboard among 40 teams with an F1-score of 71.196%.

Cancer cell segmentation is challenging since they grow in tightly packed colonies (clumps), causing adjacent cells to overlap. In this work, we proposed an automated vision-based analysis framework, 2pClPr: A 2-phase Clump Profiler for the segmentation of cancer cells in fluorescence microscopy images. In the first phase, we proposed a deep learning network, Multi-Scale Cell-Net, for coarse segmentation. Another framework, Multi-Scale Region Proposal Network (MS-RPN) was simultaneously trained in parallel to Multi-Scale Cell-Net to generate seeds for each cell. The coarse segmentation map was unable to segment the complex clumps. We proposed a novel metric, the Irregularity factor ( I_ftr ), to identify those complex clumps. Once, identified, we mapped them with the seed points generated by MS-RPN. These seeds served as the initialization points for our proposed level set framework: Weighing Repelling Force Embedded-Level Set Method (WRFe-LSM) which segments the identified complex clumps in the second phase of segmentation. The final segmentation map was generated with the segmented cells from the two phases. We conducted extensive experiments on our private dataset comprising of images from four complex cancer cell lines and obtained an Aggregated Jaccard Index (AJI) of 76.6%, 72.9%, 75.5%, and 69.7% on HeLa, MDA-MB-468, MDA-MB-231, and T-47D respectively. Further, to show the generalization ability of 2pClPr, we conducted comparative experiments on a publicly available Hematoxylin-Eosin (H&E) stained histopathological images dataset (MoNuSeg) and obtained an AJI of 66.2%. A detailed evaluation of segmentation performance on both datasets shows that 2pClPr is robust and effective.