COVID-19 Image Segmentation Algorithms Based on Conditional Generative Adversarial Network

The size and location of the lesions in CT images of novel corona virus pneumonia (COVID-19) change all the time, and the lesion areas have low contrast and blurred boundaries, resulting in difficult segmentation. To solve this problem, a COVID-19 image segmentation algorithm based on conditional generative adversarial network (CGAN) is proposed. Uses the improved DeeplabV3+ network as a generator, which enhances the extraction of multi-scale contextual features, reduces the number of network parameters and improves the training speed. A Markov discriminator with 6 fully convolutional layers is proposed instead of a common discriminator, with the aim of focusing more on the local features of the CT image. By continuously adversarial training between the generator and the discriminator, the network weights are optimised so that the final segmented image generated by the generator is infinitely close to the ground truth. On the COVID-19 CT public dataset, the area under the curve of ROC, F1-Score and dice similarity coefficient achieved 96.64%, 84.15% and 86.14% respectively. The experimental results show that the proposed algorithm is accurate and robust, and it has the possibility of becoming a safe, inexpensive, and time-saving medical assistant tool in clinical diagnosis, which provides a reference for computer-aided diagnosis. © 2022 ACM.

27th National IMI Congress

The proceedings contain 25 papers. The topics discussed include: altitude effect on melanoma epidemiology in the Veneto region: a pilot study;novel predisposition genes double a decreasing CDKN2A mutation rate: five years of (tele)- counselling and gene panel testing for hereditary melanoma within the Italian melanoma intergroup;genetic profiling of atypical deep penetrating NEVI (DPN);ultra-high frequency ultrasound monitoring of melanomas arising in congenital melanocytic nevi: a case series;a segmentation algorithm for skin melanoma regression;impact of the COVID-19 pandemic on primitive melanoma diagnoses at the IDI-IRCCS of Rome;a novel-algorithm combining static and dynamic features to identify melanoma in digital dermoscopy monitoring;and non-sentinel lymph node detection meanwhile sentinel lymph node biopsy in not-complete lymph node dissection era: a new technique for better staging and treating melanoma patients.

Deep learning model for the quantification of lung abnormalities in ILD patients

Lung fibrosis quantification from CT scans is prone to large inter and intra observer variability and its correlation with PFT is essential in the definition of disease progression. There is the need for a reliable and reproducible tool for abnormalities quantification. For this reason, a deep learning abnormalities quantification model was used to explore the correlation with PFT in ILD patients. The abnormalities segmentation model is based on 2D U-Net combined with Res Next as encoder and deep supervision and was trained on axial unenhanced chest CT scans of 199 COVID-19 patients and externally validated on 50 COVID-19 patients. Whole lungs were segmented using RadiomiX toolbox. Validation of the quantification performance was explored in a cohort of 20 ILD patients. The model performed the automatic segmentation of all abnormalities and calculate the ratio on the total lung volume ((abnormalities volume/whole lungs volume) * 100). This value is then correlated with the Forced Vital Capacity (FVC) and Diffusion Lung Capacity for carbon monoxide (DLCO) for each patient with Pearson correlation coefficient (rho). The deep learning segmentation algorithm achieved good performances (mean DSC 0.6 +/- 0.1) on the external test set. The percentage volume of disease region correlated with FVC and DLCO were the rho = -0.70402, -0.58133, respectively (P <. 001 for all). The developed algorithm performed similarly to radiologists for disease-extent contouring, which correlated with pulmonary function to assess CT images from patients with ILD. This automatic quantification tool could help in the prognosis and diagnosis of ILDs, based on the lung abnormalities extent.

Lung CT image segmentation algorithm based on improved U-net structure

Accurate segmentation of medical images can help doctors diagnose and treat diseases. In the face of the complex COVID-19 image, this paper proposes an improved U-net network segmentation model, which uses the residual network structure to deepen the network level, and adds the attention module to integrate different receptive field, global, local and spatial features to enhance the detail segmentation effect of the network. For the COVID-19 CT data set, the F1-Score, Accuracy, SE, SP and Precision of the U-Net network are 0.9176, 0.9578, 0.9669, 0.9487 and 0.8574 respectively. Compared with U-Net, our model proposed in this paper increased by 6.43%, 3.36%, 0.85%, 4.78% and 13.11% on F1-Score, Accuracy, SE, SP and Precision, respectively. The automatic and effective segmentation of COVID-19 lung CT image is realized. © 2022 IEEE.

Persistent dyspnea in post-covid patients in the absence of pulmonary embolism: added value of lung perfusion scintigraphy

Background-Aim: While there's a wide literature on CT abnormalities in COVID-19 sequelae, the role of lung perfusion scintigraphy have been scarcely investigated. Recent findings reported lung microvascular and endothelial alterations in patients recovered from COVID-19 without pulmonary embolism, presenting persistent dyspnea (POST-COVID). We compared perfusion scintigraphy and CT findings of these patients with dyspneic subjects in whom lung scintigraphy excluded pulmonary embolism (NON-COVID). In POST-COVID patients, the correlation between lung perfusion scintigraphic findings and (1) CT abnormalities, and (2) clinical/ biochemical parameters were also assessed. Methods: 24 POST-COVID and 33 NON-COVID patients who underwent lung perfusion scintigraphy for dyspnea from March 2020 to December 2021 were retrospectively enrolled. High-resolution chest CT performed 15 days before/after lung perfusion scintigraphy were available in 15/24 POST-COVID and 15/33 NON-COVID patients. From scintigraphic images counting rates for upper, middle, and lower fields were calculated in order to compute their ratio with total lung counts (UTR, MTR, and LTR, respectively) for both right and left lungs (RL and LL, respectively). CT images were analyzed using a semi-automated segmentation algorithm of 3D Slicer ( http://www.slicer.org), obtaining total, infiltrated and blood vessels' volumes, in order to calculate the infiltration rate (IR) and vascular density (VD). White blood cells, platelets, PT, INR, PTT, fibrinogen, and D-dimer of 15/24 POST-COVID patients were also collected from blood tests performed before the lung perfusion scintigraphy. Results: POST-COVID patients with persistent dyspnea showed reduced LTR (RL 22.4% ± 6.6%;LL 24.7% ± 3.1%) and higher MTR (RL 55.2% ± 5.2%;LL 49.1% ± 3.3%) compared to non- COVID patients (RL-LTR 29.6% ± 6.0%, p<0.0001;LL-LTR 28.3% ± 4.6%, p = 0.001;RL-MTR 47.3% ± 4.2%, p<0.0001;LL-MTR 47.3% ± 3.0%, p = 0.036), while UTR resulted bilaterally superimposable between the two groups. Similar IR and VD values at CT imaging were documented bilaterally in both groups. In POSTCOVID patients, no significant correlations between lung perfusion scintigraphy and CT findings were observed. Correlation analysis indicated D-dimer levels as associated with UTR (Pearson's r = 0.664;p = 0.007) and MTR (Pearson's r = - 0.555;p = 0.032), while no parameter significantly associated with LTR was observed. Conclusions: Lung perfusion scintigraphy can reveal reduced perfusion rates of lower pulmonary fields in POST-COVID patients with persistent dyspnea in the absence of pulmonary embolism, independently from CT abnormalities, infection duration and coagulation biomarkers. Although mechanisms underlying these findings need to be supported by pathological lung tissue examination, lung nonthrombotic microvascular and endothelial dysfunction may be involved.