Diagnostic Approach to Interstitial Lung Diseases Associated with Connective Tissue Diseases.

Interstitial lung disorders are a group of respiratory diseases characterized by interstitial compartment infiltration, varying degrees of infiltration, and fibrosis, with or without small airway involvement. Although some are idiopathic (e.g., idiopathic pulmonary fibrosis, idiopathic interstitial pneumonias, and sarcoidosis), the great majority have an underlying etiology, such as systemic autoimmune rheumatic disease (SARD, also called Connective Tissue Diseases or CTD), inhalational exposure to organic matter, medications, and rarely, genetic disorders. This review focuses on diagnostic approaches in interstitial lung diseases associated with SARDs. To make an accurate diagnosis, a multidisciplinary, personalized approach is required, with input from various specialties, including pulmonary, rheumatology, radiology, and pathology, to reach a consensus. In a minority of patients, a definitive diagnosis cannot be established. Their clinical presentations and prognosis can be variable even within subsets of SARDs.

Medication-induced Pulmonary Injury: A Scenario- and Pattern-based Approach to a Perplexing Problem.

Medication-induced pulmonary injury (MIPI) is a complex medical condition that has become increasingly common yet remains stubbornly difficult to diagnose. Diagnosis can be aided by combining knowledge of the most common imaging patterns caused by MIPI with awareness of which medications a patient may be exposed to in specific clinical settings. The authors describe six imaging patterns commonly associated with MIPI: sarcoidosis-like, diffuse ground-glass opacities, organizing pneumonia, centrilobular ground-glass nodules, linear-septal, and fibrotic. Subsequently, the occurrence of these patterns is discussed in the context of five different clinical scenarios and the medications and medication classes typically used in those scenarios. These scenarios and medication classes include the rheumatology or gastrointestinal clinic (disease-modifying antirheumatic agents), cardiology clinic (antiarrhythmics), hematology clinic (cytotoxic agents, tyrosine kinase inhibitors, retinoids), oncology clinic (immune modulators, tyrosine kinase inhibitors, monoclonal antibodies), and inpatient service (antibiotics, blood products). Additionally, the article draws comparisons between the appearance of MIPI and the alternative causes of lung disease typically seen in those clinical scenarios (eg, connective tissue disease-related interstitial lung disease in the rheumatology clinic and hydrostatic pulmonary edema in the cardiology clinic). Familiarity with the most common imaging patterns associated with frequently administered medications can help insert MIPI into the differential diagnosis of acquired lung disease in these scenarios. However, confident diagnosis is often thwarted by absence of specific diagnostic tests for MIPI. Instead, a working diagnosis typically relies on multidisciplinary consensus. ©RSNA, 2021.

Cavitary Coccidioidomycosis: Impact of azole antifungal therapy.

Approximately 5 to 15% of patients with pulmonary coccidioidomycosis subsequently develop pulmonary cavities. These cavities may resolve spontaneously over a number of years; however, some cavities never close, and a small proportion causes complications such as hemorrhage, pneumothorax or empyema. The impact of azole antifungal treatment on coccidioidal cavities has not been studied. Because azoles are a common treatment for symptomatic pulmonary coccidioidomycosis, we aimed to assess the impact of azole therapy on cavity closure. From January 1, 2004, through December 31, 2014, we retrospectively identified 313 patients with cavitary coccidioidomycosis and excluded 42 who had the cavity removed surgically, leaving 271 data sets available for study. Of the 271 patients, 221 (81.5%) received azole therapy during 5-year follow-up; 50 patients did not receive antifungal treatment. Among the 271 patients, cavities closed in 38 (14.0%). Statistical modeling showed that cavities were more likely to close in patients in the treated group than in the nontreated group (hazard ratio, 2.14 [95% CI: 1.45-5.66]). Cavities were less likely to close in active smokers than nonsmokers (11/41 [26.8%] vs 97/182 [53.3%]; P = 0.002) or in persons with than without diabetes (27/74 [36.5%] vs 81/149 [54.4%]; P = 0.01).We did not find an association between cavity size and closure. Our findings provide rationale for further study of treatment protocols in this subset of patients with coccidioidomycosis. LAY SUMMARY: Coccidioidomycosis, known as valley fever, is a fungal infection that infrequently causes cavities to form in the lungs, which potentially results in long-term lung symptoms. We learned that cavities closed more often in persons who received antifungal drugs, but most cavities never closed completely.

Radiologic and Pathologic Correlation in EVALI.

OBJECTIVE. The purpose of this article is to characterize the appearance on CT of e-cigarette or vaping product use-associated lung injury (EVALI) in a cohort with histopathologic evidence of this disorder. MATERIALS AND METHODS. Twenty-four patients with EVALI were identified. Chest CT examinations were reviewed by two radiologists for various chest CT findings. For comparison with pathologic findings, CT assessments were distilled into previously described patterns of EVALI seen on CT: acute lung injury (ALI), chronic eosinophilic pneumonia (CEP) or organizing pneumonia (OP), acute eosinophilic pneumonia (AEP), alveolar hemorrhage, hypersensitivity pneumonitis (HP), lipoid pneumonia, and mixed or unclassifiable patterns. RESULTS. Sixteen of 24 (67%) patients were men; the mean age was 34.5 years (range, 17-67 years). The most common CT finding was ground-glass opacities, which was present in 23 of 24 (96%) patients and the dominant finding in 18 of 24 (75%) patients. Consolidation was the next most common finding in 42% of patients. Interlobular septal thickening was present in 29%. Lobular low attenuation was conspicuous in six patients. Distribution was multifocal in 54% of patients, peripheral in 17%, and centrally predominant in 8%. Subpleural sparing was seen in 45%. The predominant CT pattern was ALI (42%), concordant with histopathologic findings in 75%; the next most predominant pattern was ground-glass opacity centrilobular nodules resembling HP (33%). A CT pattern of CEP or OP was seen in 13% of patients, all showing ALI on lung biopsy. No patient showed macroscopic lung parenchymal fat. Two patients with CT ALI patterns showed OP on histopathologic examination. Of the eight patients with ground-glass opacity centrilobular nodules resembling HP at CT, none showed HP at histopathologic examination. CONCLUSION. EVALI manifests at CT as ALI with multifocal ground-glass opacity, often with organizing consolidation, and a small centrilobular nodular pattern resembling HP.

Diagnosis of Usual Interstitial Pneumonitis in the Absence of Honeycombing: Evaluation of Specific CT Criteria With Clinical Follow-Up in 38 Patients.

OBJECTIVE: We sought to evaluate specific CT criteria for the diagnosis of usual interstitial pneumonitis (UIP) in the absence of honeycombing. These criteria included peripheral reticulation and lobular distortion; some upper lobe involvement, but a lower zone predominance; a heterogeneous appearance with areas of normal lung, minimal reticulation, and substantial distortion alternating throughout the study and often on an individual image; a nonsegmental distribution; and traction bronchiectasis. MATERIALS AND METHODS: We searched reports of CT studies performed between January 1, 2009, and January 1, 2012, to identify patients for whom UIP was a likely or probable diagnosis and reviewed the CT study for each case (n = 106). There were 38 patients who met all CT criteria and who also had a clinical diagnosis of idiopathic UIP (also known as idiopathic pulmonary fibrosis [IPF]) and follow-up of at least 6 months, as determined from the electronic medical record. We reviewed prior and subsequent CT examinations in this cohort. RESULTS: The median age of our patients was 80 years, and the duration of clinical follow-up was 6-104 months (mean, 38 months; median, 37 months). For all patients, a pulmonary medicine physician made a working diagnosis of IPF. Fifteen patients died from pulmonary complications, and 16 of the surviving patients had clinical or functional progression of disease. There were no instances in which the initial diagnosis was revised or reversed. CONCLUSION: Strict application of specific CT criteria may allow a specific diagnosis of UIP in the proper clinical setting in the absence of honeycombing.

ALK molecular phenotype in non-small cell lung cancer: CT radiogenomic characterization.

PURPOSE: To present a radiogenomic computed tomographic (CT) characterization of anaplastic lymphoma kinase (ALK)-rearranged non-small cell lung cancer (NSCLC) (ALK+). MATERIALS AND METHODS: In this HIPAA-compliant institutional review board-approved retrospective study, CT studies, ALK status, and clinical-pathologic data in 172 patients with NSCLC from three institutions were analyzed. A screen of 24 CT image traits was performed in a training set of 59 patients, followed by random forest variable selection incorporating 24 CT traits plus six clinical-pathologic covariates to identify a radiogenomic predictor of ALK+ status. This predictor was then validated in an independent cohort (n = 113). Test-for-accuracy and subset analyses were performed. A similar analysis was performed to identify a biomarker associated with shorter progression-free survival (PFS) after therapy with the ALK inhibitor crizotinib. RESULTS: ALK+ status was associated with central tumor location, absence of pleural tail, and large pleural effusion. An ALK+ radiogenomic CT status biomarker consisting of these three imaging traits with patient age of younger than 60 years showed strong discriminatory power for ALK+ status, with a sensitivity of 83.3% (15 of 18), a specificity of 77.9% (74 of 95), and an accuracy of 78.8% (89 of 113) in independent testing. The discriminatory power was particularly strong in patients with operable disease (stage IIIA or lower), with a sensitivity of 100.0% (five of five), a specificity of 88.1% (37 of 42), and an accuracy of 89.4% (42 of 47). Tumors with a disorganized vessel pattern had a shorter PFS with crizotinib therapy than tumors without this trait (11.4 vs 20.2 months, P = .041). CONCLUSION: ALK+ NSCLC has distinct characteristics at CT imaging that, when combined with clinical covariates, discriminate ALK+ from non-ALK tumors and can potentially identify patients with a shorter durable response to crizotinib.

Chest pain and diarrhea: a case of Campylobacter jejuni-associated myocarditis.

BACKGROUND: Diarrhea and chest pain are common symptoms in patients presenting to the emergency department (ED). However, rarely is a relationship between these two symptoms established in a single patient. OBJECTIVE: Describe a case of Campylobacter-associated myocarditis. CASE REPORT: A 43-year-old man with a history of hypertension presented to the ED with angina-like chest pain and a 3-day history of diarrhea. Electrocardiogram revealed ST-segment elevation in the lateral leads. Coronary angiogram revealed no obstructive coronary artery disease. Troponin T rose to 1.75 ng/mL. Cardiac magnetic resonance imaging showed subepicardial and mid-myocardial enhancement, particularly in the anterolateral wall and interventricular septum, consistent with a diagnosis of myocarditis. Stool studies were positive for Campylobacter jejuni. CONCLUSIONS: Campylobacter-associated myocarditis is rare, but performing the appropriate initial diagnostic testing, including stool cultures, is critical to making the diagnosis. Identifying the etiology of myocarditis as bacterial will ensure that appropriate treatment with antibiotics occurs in addition to any cardiology medications needed for supportive care.

Towards Foundation Models Learned from Anatomy in Medical Imaging via Self-supervision.

Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of "understanding" human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures-locality and compositionality-within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at GitHub.com/JLiangLab/Eden.

Seeking an optimal approach for Computer-aided Diagnosis of Pulmonary Embolism.

Pulmonary Embolism (PE) represents a thrombus ("blood clot"), usually originating from a lower extremity vein, that travels to the blood vessels in the lung, causing vascular obstruction and in some patients death. This disorder is commonly diagnosed using Computed Tomography Pulmonary Angiography (CTPA). Deep learning holds great promise for the Computer-aided Diagnosis (CAD) of PE. However, numerous deep learning methods, such as Convolutional Neural Networks (CNN) and Transformer-based models, exist for a given task, causing great confusion regarding the development of CAD systems for PE. To address this confusion, we present a comprehensive analysis of competing deep learning methods applicable to PE diagnosis based on four datasets. First, we use the RSNA PE dataset, which includes (weak) slice-level and exam-level labels, for PE classification and diagnosis, respectively. At the slice level, we compare CNNs with the Vision Transformer (ViT) and the Swin Transformer. We also investigate the impact of self-supervised versus (fully) supervised ImageNet pre-training, and transfer learning over training models from scratch. Additionally, at the exam level, we compare sequence model learning with our proposed transformer-based architecture, Embedding-based ViT (E-ViT). For the second and third datasets, we utilize the CAD-PE Challenge Dataset and Ferdowsi University of Mashad's PE Dataset, where we convert (strong) clot-level masks into slice-level annotations to evaluate the optimal CNN model for slice-level PE classification. Finally, we use our in-house PE-CAD dataset, which contains (strong) clot-level masks. Here, we investigate the impact of our vessel-oriented image representations and self-supervised pre-training on PE false positive reduction at the clot level across image dimensions (2D, 2.5D, and 3D). Our experiments show that (1) transfer learning boosts performance despite differences between photographic images and CTPA scans; (2) self-supervised pre-training can surpass (fully) supervised pre-training; (3) transformer-based models demonstrate comparable performance but slower convergence compared with CNNs for slice-level PE classification; (4) model trained on the RSNA PE dataset demonstrates promising performance when tested on unseen datasets for slice-level PE classification; (5) our E-ViT framework excels in handling variable numbers of slices and outperforms sequence model learning for exam-level diagnosis; and (6) vessel-oriented image representation and self-supervised pre-training both enhance performance for PE false positive reduction across image dimensions. Our optimal approach surpasses state-of-the-art results on the RSNA PE dataset, enhancing AUC by 0.62% (slice-level) and 2.22% (exam-level). On our in-house PE-CAD dataset, 3D vessel-oriented images improve performance from 80.07% to 91.35%, a remarkable 11% gain. Codes are available at GitHub.com/JLiangLab/CAD_PE.

Stepwise incremental pretraining for integrating discriminative, restorative, and adversarial learning.

We have developed a United framework that integrates three self-supervised learning (SSL) ingredients (discriminative, restorative, and adversarial learning), enabling collaborative learning among the three learning ingredients and yielding three transferable components: a discriminative encoder, a restorative decoder, and an adversary encoder. To leverage this collaboration, we redesigned nine prominent self-supervised methods, including Rotation, Jigsaw, Rubik's Cube, Deep Clustering, TransVW, MoCo, BYOL, PCRL, and Swin UNETR, and augmented each with its missing components in a United framework for 3D medical imaging. However, such a United framework increases model complexity, making 3D pretraining difficult. To overcome this difficulty, we propose stepwise incremental pretraining, a strategy that unifies the pretraining, in which a discriminative encoder is first trained via discriminative learning, the pretrained discriminative encoder is then attached to a restorative decoder, forming a skip-connected encoder-decoder, for further joint discriminative and restorative learning. Last, the pretrained encoder-decoder is associated with an adversarial encoder for final full discriminative, restorative, and adversarial learning. Our extensive experiments demonstrate that the stepwise incremental pretraining stabilizes United models pretraining, resulting in significant performance gains and annotation cost reduction via transfer learning in six target tasks, ranging from classification to segmentation, across diseases, organs, datasets, and modalities. This performance improvement is attributed to the synergy of the three SSL ingredients in our United framework unleashed through stepwise incremental pretraining. Our codes and pretrained models are available at GitHub.com/JLiangLab/StepwisePretraining.

Self-supervised learning for medical image analysis: Discriminative, restorative, or adversarial?

Discriminative, restorative, and adversarial learning have proven beneficial for self-supervised learning schemes in computer vision and medical imaging. Existing efforts, however, fail to capitalize on the potentially synergistic effects these methods may offer in a ternary setup, which, we envision can significantly benefit deep semantic representation learning. Towards this end, we developed DiRA, the first framework that unites discriminative, restorative, and adversarial learning in a unified manner to collaboratively glean complementary visual information from unlabeled medical images for fine-grained semantic representation learning. Our extensive experiments demonstrate that DiRA: (1) encourages collaborative learning among three learning ingredients, resulting in more generalizable representation across organs, diseases, and modalities; (2) outperforms fully supervised ImageNet models and increases robustness in small data regimes, reducing annotation cost across multiple medical imaging applications; (3) learns fine-grained semantic representation, facilitating accurate lesion localization with only image-level annotation; (4) improves reusability of low/mid-level features; and (5) enhances restorative self-supervised approaches, revealing that DiRA is a general framework for united representation learning. Code and pretrained models are available at https://github.com/JLiangLab/DiRA.

Anomalous origin of the circumflex artery from the right pulmonary artery.

Anomalous origin of the circumflex artery from the pulmonary artery (ACxAPA) is a rare but clinically significant condition in which the circumflex artery arises from either the main pulmonary artery or one of its main branches. Untreated patients with ACxAPA may develop severe heart failure or sudden cardiac death. Diagnosis is established with either catheter or CT angiography. We present a case of an adult male with no prior known cardiac history who was found to have ACxAPA after presenting to our institution in acute decompensated heart failure.

Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performance.

Deep learning nowadays offers expert-level and sometimes even super-expert-level performance, but achieving such performance demands massive annotated data for training (e.g., Google's proprietary CXR Foundation Model (CXR-FM) was trained on 821,544 labeled and mostly private chest X-rays (CXRs)). Numerous datasets are publicly available in medical imaging but individually small and heterogeneous in expert labels. We envision a powerful and robust foundation model that can be trained by aggregating numerous small public datasets. To realize this vision, we have developed Ark, a framework that accrues and reuses knowledge from heterogeneous expert annotations in various datasets. As a proof of concept, we have trained two Ark models on 335,484 and 704,363 CXRs, respectively, by merging several datasets including ChestX-ray14, CheXpert, MIMIC-II, and VinDr-CXR, evaluated them on a wide range of imaging tasks covering both classification and segmentation via fine-tuning, linear-probing, and gender-bias analysis, and demonstrated our Ark's superior and robust performance over the state-of-the-art (SOTA) fully/self-supervised baselines and Google's proprietary CXR-FM. This enhanced performance is attributed to our simple yet powerful observation that aggregating numerous public datasets diversifies patient populations and accrues knowledge from diverse experts, yielding unprecedented performance yet saving annotation cost. With all codes and pretrained models released at GitHub.com/JLiangLab/Ark, we hope that Ark exerts an important impact on open science, as accruing and reusing knowledge from expert annotations in public datasets can potentially surpass the performance of proprietary models trained on unusually large data, inspiring many more researchers worldwide to share codes and datasets to build open foundation models, accelerate open science, and democratize deep learning for medical imaging.

Lymphoid Interstitial Pneumonia (LIP) Revisited: A Critical Reappraisal of the Histologic Spectrum of "Radiologic" and "Pathologic" LIP in the Context of Diffuse Benign Lymphoid Proliferations of the Lung.

The use of lymphoid interstitial pneumonia (LIP) as a diagnostic term has changed considerably since its introduction. Utilizing a multi-institutional collection of 201 cases from the last 20 years that demonstrate features associated with the LIP rubric, we compared cases meeting strict histologic criteria of LIP per American Thoracic Society (ATS)/European Respiratory Society (ERS) consensus ("pathologic LIP"; n=62) with cystic cases fulfilling radiologic ATS/ERS criteria ("radiologic LIP"; n=33) and with other diffuse benign lymphoid proliferations. "Pathologic LIP" was associated with immune dysregulation including autoimmune disorders and immune deficiency, whereas "radiologic LIP" was only seen with autoimmune disorders. No case of idiopathic LIP was found. On histology, "pathologic LIP" represented a subgroup of 70% (62/88) of cases with the distinctive pattern of diffuse expansile lymphoid infiltrates. In contrast, "radiologic LIP" demonstrated a broad spectrum of inflammatory patterns, airway-centered inflammation being most common (52%; 17/33). Only 5 cases with radiologic cysts also met consensus ATS/ERS criteria for "pathologic LIP." Overall, broad overlap was observed with the remaining study cases that failed to meet consensus criteria for "radiologic LIP" and/or "pathologic LIP." These data raise concerns about the practical use of the term LIP as currently defined. What radiologists and pathologist encounter as LIP differs remarkably, but neither "radiologic LIP" nor "pathologic LIP" present with sufficiently distinct findings to delineate such cases from other patterns of diffuse benign lymphoid proliferations. As a result of this study, we believe LIP should be abandoned as a pathologic and radiologic diagnosis.

CT findings and long-term mortality after pulmonary embolism.

OBJECTIVE: The utility of CT findings in predicting long-term mortality in patients with acute pulmonary embolism (PE) is unknown. The purpose of this study is to retrospectively determine whether three CT findings--increased embolic burden, interventricular septal bowing toward the left ventricle, and right ventricle-to-left ventricle (RV/LV) diameter ratio greater than 1--are independent predictors of long-term all-cause mortality after acute PE. MATERIALS AND METHODS: A total of 1105 patients (47% female; mean age, 63 ± 16 years) with CT scans positive for PE from January 1, 1997, to December 31, 2002, were included. Scans were independently interpreted by two observers, with a third independent observer reviewing discrepant cases. CT findings and clinical information were compared with all-cause mortality using univariate and multivariate logistic regression analyses. RESULTS: The median duration of survival was 6.2 years following acute PE, with estimated 10-year survival of 37.4%. CT-derived embolic burden was associated with a very small decrease in long-term all-cause mortality in both univariate (hazard ratio [HR], 0.97; p < 0.001) and multivariate (HR, 0.97; p < 0.001) analyses. Interventricular septal bowing and RV/LV diameter ratio were not significantly associated with long-term all-cause mortality. CONCLUSION: CT findings are not predictive of decreased long-term survival after acute PE.

CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical Imaging.

Recently, self-supervised instance discrimination methods have achieved significant success in learning visual representations from unlabeled photographic images. However, given the marked differences between photographic and medical images, the efficacy of instance-based objectives, focusing on learning the most discriminative global features in the image (i.e., wheels in bicycle), remains unknown in medical imaging. Our preliminary analysis showed that high global similarity of medical images in terms of anatomy hampers instance discrimination methods for capturing a set of distinct features, negatively impacting their performance on medical downstream tasks. To alleviate this limitation, we have developed a simple yet effective self-supervised framework, called Context-Aware instance Discrimination (CAiD). CAiD aims to improve instance discrimination learning by providing finer and more discriminative information encoded from a diverse local context of unlabeled medical images. We conduct a systematic analysis to investigate the utility of the learned features from a three-pronged perspective: (i) generalizability and transferability, (ii) separability in the embedding space, and (iii) reusability. Our extensive experiments demonstrate that CAiD (1) enriches representations learned from existing instance discrimination methods; (2) delivers more discriminative features by adequately capturing finer contextual information from individual medial images; and (3) improves reusability of low/mid-level features compared to standard instance discriminative methods. As open science, all codes and pre-trained models are available on our GitHub page: https://github.com/JLiangLab/CAiD.

DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis.

Discriminative learning, restorative learning, and adversarial learning have proven beneficial for self-supervised learning schemes in computer vision and medical imaging. Existing efforts, however, omit their synergistic effects on each other in a ternary setup, which, we envision, can significantly benefit deep semantic representation learning. To realize this vision, we have developed DiRA, the first framework that unites discriminative, restorative, and adversarial learning in a unified manner to collaboratively glean complementary visual information from unlabeled medical images for fine-grained semantic representation learning. Our extensive experiments demonstrate that DiRA (1) encourages collaborative learning among three learning ingredients, resulting in more generalizable representation across organs, diseases, and modalities; (2) outperforms fully supervised ImageNet models and increases robustness in small data regimes, reducing annotation cost across multiple medical imaging applications; (3) learns fine-grained semantic representation, facilitating accurate lesion localization with only image-level annotation; and (4) enhances state-of-the-art restorative approaches, revealing that DiRA is a general mechanism for united representation learning. All code and pretrained models are available at https://github.com/JLiangLab/DiRA.

Discriminative, Restorative, and Adversarial Learning: Stepwise Incremental Pretraining.

Uniting three self-supervised learning (SSL) ingredients (discriminative, restorative, and adversarial learning) enables collaborative representation learning and yields three transferable components: a discriminative encoder, a restorative decoder, and an adversary encoder. To leverage this advantage, we have redesigned five prominent SSL methods, including Rotation, Jigsaw, Rubik's Cube, Deep Clustering, and TransVW, and formulated each in a United framework for 3D medical imaging. However, such a United framework increases model complexity and pretraining difficulty. To overcome this difficulty, we develop a stepwise incremental pretraining strategy, in which a discriminative encoder is first trained via discriminative learning, the pretrained discriminative encoder is then attached to a restorative decoder, forming a skip-connected encoder-decoder, for further joint discriminative and restorative learning, and finally, the pretrained encoder-decoder is associated with an adversarial encoder for final full discriminative, restorative, and adversarial learning. Our extensive experiments demonstrate that the stepwise incremental pretraining stabilizes United models training, resulting in significant performance gains and annotation cost reduction via transfer learning for five target tasks, encompassing both classification and segmentation, across diseases, organs, datasets, and modalities. This performance is attributed to the synergy of the three SSL ingredients in our United framework unleashed via stepwise incremental pretraining. All codes and pretrained models are available at GitHub.com/JLiangLab/StepwisePretraining.